Merged timeline of 111 items — blog publish times and listing timestamps, cut at midnight . Page 3 of 3.
A consortium of 9 Indian academic institutions and 60+ researchers has built BharatGen — India's answer to the sovereign AI question. Four model families, 22 scheduled languages, and ₹988.6 crore from the IndiaAI Mission. Unveiled June 15 in Nice at Bharat Innovates 2026.
One week ago "loop engineering" was a term most developers hadn't heard. Today it is trending across X with 2,200+ posts, championed by Anthropic's Boris Cherny and OpenAI's Peter Steinberger, critiqued by Matt Pocock, and joked about by everyone who has watched Claude say "You're right to push back! I over-engineered this!" 87 times in a row. Here is the full picture.
A 7B parameter model at full float32 precision needs 28GB of VRAM — more than an RTX 4090 has. Quantization is the technique that makes local AI practical: reduce numerical precision, shrink the model, run it on hardware you own. Here is how it works, why quality holds up better than expected, and what you should actually run on your GPU in 2026.
Prompt engineering optimizes a single instruction you type by hand. Loop engineering optimizes the autonomous system that decides what to prompt, when to prompt it, and whether the result is acceptable. Here's what it means and why it matters.
Settings passed on the CLI vanish when the session ends. settings.json makes them permanent. This reference covers every key you can put in .claude/settings.json—from model selection and permission globs to MCP server definitions, PostToolUse hooks, and custom agents—plus a clear project vs. user vs. local split so your team shares the right config.
Claude Code exposes 90+ slash commands for setup, parallel agents, review, memory, and shipping. This is the complete reference: what each command does, when to use it, and how they fit a typical workflow.
At Code with Claude Tokyo, Anthropic shipped scheduled deployments and environment-variable vaults in public beta for Claude Managed Agents, plus general availability for dynamic workflows in Claude Code—agents that run on a schedule, use tools securely, and tackle bigger parallel jobs.
cmux transforms AI-assisted development with a Ghostty-based terminal that understands when agents need your attention. With vertical tabs showing git status, PR numbers, listening ports, and notification previews, plus a scriptable browser and native Claude Code Teams support, it's the terminal built for the AI coding era.
Mario Zechner's Pi, extended with production-grade harness engineering: hashline edits that eliminate whitespace battles, LSP-driven renames, lldb/dlv/debugpy integration, 14-provider web_search, and task isolation across APFS/btrfs/overlayfs—5.5k stars and climbing.
At a San Francisco developer event, Anthropic rolled out Dreaming (research preview) to let Claude Managed Agents learn from session transcripts, plus public betas for multiagent orchestration (up to 20 parallel agents), outcomes loops (rubric-based self-checks), and webhooks for external notifications.
The Caveman skill compresses assistant surface prose (lite, full, ultra) while keeping code intact. Here is 2026 frontier pricing, output-vs-input math, and when brevity helps quality—not only cost.
